Universal approximation on the hypersphere

DOI10.1080/03610926.2021.1904988OpenAlexW3144048863MaRDI QIDQ5057345

Tin Lok James Ng, Kwok-Kun Kwong

Publication date: 16 December 2022

Published in: Communications in Statistics - Theory and Methods (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2004.06328

zbMATH Keywords

universal approximationfinite mixturespherical convolutionvon-Mises-Fisher distribution

Mathematics Subject Classification ID

Statistics (62-XX)

Uses Software

• bayesm

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Universal series induced by approximate identities and some relevant applications
• Density estimation through convex combinations of densities: Approximation and estimation bounds
• An antipodally symmetric distribution on the sphere
• Multilayer feedforward networks are universal approximators
• Optimal directional statistic for general regression
• The multivariate Watson distribution: maximum-likelihood estimation and other aspects
• On the Expressive Power of Deep Architectures
• Approximation of probability distributions by convex mixtures of Gaussian measures
• Approximation by spherical convolution
• Model-Based Clustering, Discriminant Analysis, and Density Estimation
• Funk-Hecke Formula for Orthogonal Polynomials on Spheres and on Balls
• On approximations via convolution-defined mixture models
• Approximation by finite mixtures of continuous density functions that vanish at infinity
• Approximation by superpositions of a sigmoidal function
• Approximation of probability density functions via location-scale finite mixtures in Lebesgue spaces

This page was built for publication: Universal approximation on the hypersphere